Skip to content

Commit d966f98

Browse files
MengzhangLIJunjun2016
MengzhangLI
and
Junjun2016
authored
[Feature] Support ICNet (open-mmlab#884)
* add icnet backbone * add icnet head * add icnet configs * nclass -> num_classes * Support ICNet * ICNet * ICNet * Add ICNeck * Add ICNeck * Add ICNeck * Add ICNeck * Adding unittest * Uploading models & logs * Uploading models & logs * add comment * smaller test_swin.py * try to delete test_swin.py * delete test_unet.py * delete test_unet.py * temp * smaller test_unet.py Co-authored-by: Junjun2016 <[email protected]>
1 parent 10886b0 commit d966f98

30 files changed

+953
-112
lines changed

‎README.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -79,6 +79,7 @@ Supported methods:
7979
- [x] [PSANet (ECCV'2018)](configs/psanet)
8080
- [x] [DeepLabV3+ (CVPR'2018)](configs/deeplabv3plus)
8181
- [x] [UPerNet (ECCV'2018)](configs/upernet)
82+
- [x] [ICNet (ECCV'2018)](configs/icnet)
8283
- [x] [NonLocal Net (CVPR'2018)](configs/nonlocal_net)
8384
- [x] [EncNet (CVPR'2018)](configs/encnet)
8485
- [x] [Semantic FPN (CVPR'2019)](configs/sem_fpn)

‎README_zh-CN.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -78,6 +78,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
7878
- [x] [PSANet (ECCV'2018)](configs/psanet)
7979
- [x] [DeepLabV3+ (CVPR'2018)](configs/deeplabv3plus)
8080
- [x] [UPerNet (ECCV'2018)](configs/upernet)
81+
- [x] [ICNet (ECCV'2018)](configs/icnet)
8182
- [x] [NonLocal Net (CVPR'2018)](configs/nonlocal_net)
8283
- [x] [EncNet (CVPR'2018)](configs/encnet)
8384
- [x] [Semantic FPN (CVPR'2019)](configs/sem_fpn)

‎configs/_base_/datasets/cityscapes_832x832.py‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
_base_ = './cityscapes.py'
2+
img_norm_cfg = dict(
3+
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
4+
crop_size = (832, 832)
5+
train_pipeline = [
6+
dict(type='LoadImageFromFile'),
7+
dict(type='LoadAnnotations'),
8+
dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
9+
dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
10+
dict(type='RandomFlip', prob=0.5),
11+
dict(type='PhotoMetricDistortion'),
12+
dict(type='Normalize', **img_norm_cfg),
13+
dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
14+
dict(type='DefaultFormatBundle'),
15+
dict(type='Collect', keys=['img', 'gt_semantic_seg']),
16+
]
17+
test_pipeline = [
18+
dict(type='LoadImageFromFile'),
19+
dict(
20+
type='MultiScaleFlipAug',
21+
img_scale=(2048, 1024),
22+
# img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
23+
flip=False,
24+
transforms=[
25+
dict(type='Resize', keep_ratio=True),
26+
dict(type='RandomFlip'),
27+
dict(type='Normalize', **img_norm_cfg),
28+
dict(type='ImageToTensor', keys=['img']),
29+
dict(type='Collect', keys=['img']),
30+
])
31+
]
32+
data = dict(
33+
train=dict(pipeline=train_pipeline),
34+
val=dict(pipeline=test_pipeline),
35+
test=dict(pipeline=test_pipeline))

‎configs/_base_/models/icnet_r50-d8.py‎

Lines changed: 74 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,74 @@
1+
# model settings
2+
norm_cfg = dict(type='SyncBN', requires_grad=True)
3+
model = dict(
4+
type='EncoderDecoder',
5+
backbone=dict(
6+
type='ICNet',
7+
backbone_cfg=dict(
8+
type='ResNetV1c',
9+
in_channels=3,
10+
depth=50,
11+
num_stages=4,
12+
out_indices=(0, 1, 2, 3),
13+
dilations=(1, 1, 2, 4),
14+
strides=(1, 2, 1, 1),
15+
norm_cfg=norm_cfg,
16+
norm_eval=False,
17+
style='pytorch',
18+
contract_dilation=True),
19+
in_channels=3,
20+
layer_channels=(512, 2048),
21+
light_branch_middle_channels=32,
22+
psp_out_channels=512,
23+
out_channels=(64, 256, 256),
24+
norm_cfg=norm_cfg,
25+
align_corners=False,
26+
),
27+
neck=dict(
28+
type='ICNeck',
29+
in_channels=(64, 256, 256),
30+
out_channels=128,
31+
norm_cfg=norm_cfg,
32+
align_corners=False),
33+
decode_head=dict(
34+
type='FCNHead',
35+
in_channels=128,
36+
channels=128,
37+
num_convs=1,
38+
in_index=2,
39+
dropout_ratio=0,
40+
num_classes=19,
41+
norm_cfg=norm_cfg,
42+
concat_input=False,
43+
align_corners=False,
44+
loss_decode=dict(
45+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
46+
auxiliary_head=[
47+
dict(
48+
type='FCNHead',
49+
in_channels=128,
50+
channels=128,
51+
num_convs=1,
52+
num_classes=19,
53+
in_index=0,
54+
norm_cfg=norm_cfg,
55+
concat_input=False,
56+
align_corners=False,
57+
loss_decode=dict(
58+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
59+
dict(
60+
type='FCNHead',
61+
in_channels=128,
62+
channels=128,
63+
num_convs=1,
64+
num_classes=19,
65+
in_index=1,
66+
norm_cfg=norm_cfg,
67+
concat_input=False,
68+
align_corners=False,
69+
loss_decode=dict(
70+
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
71+
],
72+
# model training and testing settings
73+
train_cfg=dict(),
74+
test_cfg=dict(mode='whole'))

‎configs/bisenetv1/README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@
3232
| BiSeNetV1 (No Pretrain) | R-18-D32 | 1024x1024 | 160000 | 5.69 | 31.77 | 74.44 | 77.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239-c55e78e2.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_4x4_1024x1024_160k_cityscapes_20210922_172239.log.json) |
3333
| BiSeNetV1| R-18-D32 | 1024x1024 | 160000 | 5.69 | 31.77 | 74.37 | 76.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251-8ba80eff.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210905_220251.log.json) |
3434
| BiSeNetV1 (4x8) | R-18-D32 | 1024x1024 | 160000 | 11.17 | 31.77 | 75.16 | 77.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322-bb8db75f.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes/bisenetv1_r18-d32_in1k-pre_4x8_1024x1024_160k_cityscapes_20210905_220322.log.json) |
35-
| BiSeNetV1 (No Pretrain) | R-50-D32 | 1024x1024 | 160000 | 3.3 | 7.71 | 76.92 | 78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json) |
35+
| BiSeNetV1 (No Pretrain) | R-50-D32 | 1024x1024 | 160000 | 15.39 | 7.71 | 76.92 | 78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json) |
3636
| BiSeNetV1 | R-50-D32 | 1024x1024 | 160000 | 15.39 | 7.71 | 77.68 | 79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
3737

3838
Note:

‎configs/bisenetv1/bisenetv1.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -92,7 +92,7 @@ Models:
9292
batch size: 1
9393
mode: FP32
9494
resolution: (1024,1024)
95-
memory (GB): 3.3
95+
memory (GB): 15.39
9696
Results:
9797
- Task: Semantic Segmentation
9898
Dataset: Cityscapes

‎configs/icnet/README.md‎

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
# ICNet for Real-time Semantic Segmentation on High-resolution Images
2+
3+
## Introduction
4+
5+
<!-- [ALGORITHM] -->
6+
7+
<a href="https://github.com/hszhao/ICNet">Official Repo</a>
8+
9+
<a href="https://github.com/open-mmlab/mmsegmentation/blob/v0.18.0/mmseg/models/necks/ic_neck.py#L77">Code Snippet</a>
10+
11+
<details>
12+
<summary align="right"><a href="https://arxiv.org/abs/1704.08545">ICNet (ECCV'2018)</a></summary>
13+
14+
```latext
15+
@inproceedings{zhao2018icnet,
16+
title={Icnet for real-time semantic segmentation on high-resolution images},
17+
author={Zhao, Hengshuang and Qi, Xiaojuan and Shen, Xiaoyong and Shi, Jianping and Jia, Jiaya},
18+
booktitle={Proceedings of the European conference on computer vision (ECCV)},
19+
pages={405--420},
20+
year={2018}
21+
}
22+
```
23+
24+
</details>
25+
26+
## Results and models
27+
28+
### Cityscapes
29+
30+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
31+
| ------ | ---------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
32+
| ICNet | R-18-D8 | 832x832 | 80000 | 1.70 | 27.12 | 68.14 | 70.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r18-d8_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521-2e36638d.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_80k_cityscapes/icnet_r18-d8_832x832_80k_cityscapes_20210925_225521.log.json) |
33+
| ICNet | R-18-D8 | 832x832 | 160000 | - | - | 71.64 | 74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r18-d8_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153-2c6eb6e0.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_832x832_160k_cityscapes/icnet_r18-d8_832x832_160k_cityscapes_20210925_230153.log.json) |
34+
| ICNet (in1k-pre) | R-18-D8 | 832x832 | 80000 | - | - | 72.51 | 74.78 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354-1cbe3022.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes/icnet_r18-d8_in1k-pre_832x832_80k_cityscapes_20210925_230354.log.json) |
35+
| ICNet (in1k-pre) | R-18-D8 | 832x832 | 160000 | - | - | 74.43 | 76.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702-619c8ae1.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes/icnet_r18-d8_in1k-pre_832x832_160k_cityscapes_20210926_052702.log.json) |
36+
| ICNet | R-50-D8 | 832x832 | 80000 | 2.53 | 20.08 | 68.91 | 69.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r50-d8_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625-c6407341.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_80k_cityscapes/icnet_r50-d8_832x832_80k_cityscapes_20210926_044625.log.json) |
37+
| ICNet | R-50-D8 | 832x832 | 160000 | - | - | 73.82 | 75.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r50-d8_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612-a95f0d4e.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_832x832_160k_cityscapes/icnet_r50-d8_832x832_160k_cityscapes_20210925_232612.log.json) |
38+
| ICNet (in1k-pre) | R-50-D8 | 832x832 | 80000 | - | - | 74.58 | 76.41 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943-1743dc7b.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes/icnet_r50-d8_in1k-pre_832x832_80k_cityscapes_20210926_032943.log.json) |
39+
| ICNet (in1k-pre) | R-50-D8 | 832x832 | 160000 | - | - | 76.29 | 78.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715-ce310aea.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes/icnet_r50-d8_in1k-pre_832x832_160k_cityscapes_20210926_042715.log.json) |
40+
| ICNet | R-101-D8 | 832x832 | 80000 | 3.08 | 16.95 | 70.28 | 71.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r101-d8_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447-b52f936e.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_80k_cityscapes/icnet_r101-d8_832x832_80k_cityscapes_20210926_072447.log.json) |
41+
| ICNet | R-101-D8 | 832x832 | 160000 | - | - | 73.80 | 76.10 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r101-d8_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350-3a1ebf1a.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_832x832_160k_cityscapes/icnet_r101-d8_832x832_160k_cityscapes_20210926_092350.log.json) |
42+
| ICNet (in1k-pre) | R-101-D8 | 832x832 | 80000 | - | - | 75.57 | 77.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414-7ceb12c5.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes/icnet_r101-d8_in1k-pre_832x832_80k_cityscapes_20210926_020414.log.json) |
43+
| ICNet (in1k-pre) | R-101-D8 | 832x832 | 160000 | - | - | 76.15 | 77.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612-9484ae8a.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/icnet/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes/icnet_r101-d8_in1k-pre_832x832_160k_cityscapes_20210925_232612.log.json) |
44+
45+
Note: `in1k-pre` means pretrained model is used.

0 commit comments

Comments
 (0)